The patch titled
Subject: khugepaged: drain all LRU caches before scanning pages
has been removed from the -mm tree. Its filename was
khugepaged-drain-all-lru-caches-before-scanning-pages.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: khugepaged: drain all LRU caches before scanning pages
Having a page in LRU add cache offsets page refcount and gives
false-negative on PageLRU(). It reduces collapse success rate.
Drain all LRU add caches before scanning. It happens relatively rare and
should not disturb the system too much.
Link: http://lkml.kernel.org/r/20200416160026.16538-4-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Reviewed-by: William Kucharski <william.kucharski@xxxxxxxxxx>
Reviewed-by: Zi Yan <ziy@xxxxxxxxxx>
Tested-by: Zi Yan <ziy@xxxxxxxxxx>
Acked-by: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Ralph Campbell <rcampbell@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/khugepaged.c | 2 ++
1 file changed, 2 insertions(+)
--- a/mm/khugepaged.c~khugepaged-drain-all-lru-caches-before-scanning-pages
+++ a/mm/khugepaged.c
@@ -2079,6 +2079,8 @@ static void khugepaged_do_scan(void)
barrier(); /* write khugepaged_pages_to_scan to local stack */
+ lru_add_drain_all();
+
while (progress < pages) {
if (!khugepaged_prealloc_page(&hpage, &wait))
break;
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
